Stretch - Elliot

Table of contents

• QUESTION 1

import pandas as pd
import polars as pl
import numpy as np
from lets_plot import *

LetsPlot.setup_html(isolated_frame=True)

# df_url = pd.read_csv("https://github.com/byuidatascience/data4names/raw/master/data-raw/names_year/names_year.csv")
df = pd.read_csv("names_year.csv")

# df_url_pl = pl.read_csv("https://github.com/byuidatascience/data4names/raw/master/data-raw/names_year/names_year.csv", infer_schema_length=100000)
df_pl = pl.read_csv("names_year.csv", infer_schema_length=100000)

QUESTION 1

1. Reproducing the Elliot chart from the assignmet page by using the names_year.csv file.

# Pandas
df_ell = df.query('name == ["Elliot"]')
ell = (
    ggplot(data=df_ell)
    + geom_line(mapping = aes(x = 'year', y = 'Total', color='name'))
    + scale_color_manual(values={'Elliot': 'blue'})
    + scale_x_continuous(limits=[1950,2025], format = 'd', expand=[0,0])
    + scale_y_continuous(format='d')
    + labs(
        title="Elliot... What?"
    )
    + theme(panel_grid=element_line(linetype=1, color = "white"),
        panel_background=element_rect(fill="#e5ecf6", linetype=0),
        axis_line_x=element_blank(),
        axis_ticks_x=element_blank()
        )
    + geom_text(x = 1982, y = 1300, label="E.T. Released", hjust="right", size=6)
    + geom_text(x = 1985, y = 1300, label="Second Released", hjust="left", size=6)
    + geom_text(x = 2002, y = 1300, label="Third Released", hjust="left", size=6)
    + geom_vline(xintercept=1982, color="red", linetype="dashed")
    + geom_vline(xintercept=1985, color="red", linetype="dashed")
    + geom_vline(xintercept=2002, color="red", linetype="dashed")
)
display(ell)
ggsave(ell, filename="elliot_pandas.svg", path="./plots/")
# Polars
print(f"\nUsing Polars")
df_ell_pl = df_pl.filter(pl.col('name').is_in(["Elliot"]))
ell_pl = (
    ggplot(data=df_ell_pl)
    + geom_line(mapping = aes(x = 'year', y = 'Total', color='name'))
    + scale_color_manual(values={'Elliot': 'blue'})
    + scale_x_continuous(limits=[1950,2025], format = 'd', expand=[0, 0])
    + scale_y_continuous(format='d')
    + labs(
        title="Elliot... What?"
    )
    + theme(panel_grid=element_line(linetype=1, color = "white"),
        panel_background=element_rect(fill="#e5ecf6", linetype=0),
        axis_line_x=element_blank(),
        axis_ticks_x=element_blank()
        )
    + geom_text(x = 1982, y = 1300, label="E.T. Released", hjust="right", size=6)
    + geom_text(x = 1985, y = 1300, label="Second Released", hjust="left", size=6)
    + geom_text(x = 2002, y = 1300, label="Third Released", hjust="left", size=6)
    + geom_vline(xintercept=1982, color="red", linetype="dashed")
    + geom_vline(xintercept=1985, color="red", linetype="dashed")
    + geom_vline(xintercept=2002, color="red", linetype="dashed")
)
display(ell_pl)
# the sv is simply to suppress the output
sv = ggsave(ell_pl, filename="elliot_polars.svg", path="./plots/")

Using Polars